© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106350
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations related to environmental and safety standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ìģt
    -0.09
    ÅĻÃŃd
    -0.08
    ibold
    -0.07
    اÙħبر
    -0.07
     Templ
    -0.07
    ãĤĥ
    -0.07
     (%)
    -0.07
    erno
    -0.07
    δή
    -0.07
    оÑĤе
    -0.07
    POSITIVE LOGITS
    )
    0.06
     pun
    0.06
    ;
    0.06
    ),
    0.06
    ABC
    0.06
    alık
    0.05
     Omn
    0.05
     Fran
    0.05
     subt
    0.05
    δÏħ
    0.05
    Activations Density 0.039%

    No Known Activations